1 files changed, 38 insertions, 30 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 91d123938cef..60ce1190307b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -384,7 +384,7 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 	/*
 	 * Things reading via commit roots that don't have normal protection,
 	 * like send, can have a really old block in cache that may point at a
-	 * block that has been free'd and re-allocated.  So don't clear uptodate
+	 * block that has been freed and re-allocated.  So don't clear uptodate
 	 * if we find an eb that is under IO (dirty/writeback) because we could
 	 * end up reading in the stale data and then writing it back out and
 	 * making everybody very sad.
@@ -418,7 +418,7 @@ static int btrfs_check_super_csum(char *raw_disk_sb)
 		/*
 		 * The super_block structure does not span the whole
 		 * BTRFS_SUPER_INFO_SIZE range, we expect that the unused space
-		 * is filled with zeros and is included in the checkum.
+		 * is filled with zeros and is included in the checksum.
 		 */
 		crc = btrfs_csum_data(raw_disk_sb + BTRFS_CSUM_SIZE,
 				crc, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE);
@@ -600,7 +600,7 @@ static noinline int check_leaf(struct btrfs_root *root,
 
 		/*
 		 * Check to make sure that we don't point outside of the leaf,
-		 * just incase all the items are consistent to eachother, but
+		 * just in case all the items are consistent to each other, but
 		 * all point outside of the leaf.
 		 */
 		if (btrfs_item_end_nr(leaf, slot) >
@@ -1098,7 +1098,7 @@ void readahead_tree_block(struct btrfs_root *root, u64 bytenr)
 	struct inode *btree_inode = root->fs_info->btree_inode;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
+	if (IS_ERR(buf))
 		return;
 	read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
 				 buf, 0, WAIT_NONE, btree_get_extent, 0);
@@ -1114,7 +1114,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr,
 	int ret;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
+	if (IS_ERR(buf))
 		return 0;
 
 	set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);
@@ -1147,7 +1147,8 @@ struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
 						 u64 bytenr)
 {
 	if (btrfs_test_is_dummy_root(root))
-		return alloc_test_extent_buffer(root->fs_info, bytenr);
+		return alloc_test_extent_buffer(root->fs_info, bytenr,
+				root->nodesize);
 	return alloc_extent_buffer(root->fs_info, bytenr);
 }
 
@@ -1171,8 +1172,8 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
 	int ret;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(buf))
+		return buf;
 
 	ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
 	if (ret) {
@@ -1314,14 +1315,16 @@ static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info,
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 /* Should only be used by the testing infrastructure */
-struct btrfs_root *btrfs_alloc_dummy_root(void)
+struct btrfs_root *btrfs_alloc_dummy_root(u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_root *root;
 
 	root = btrfs_alloc_root(NULL, GFP_KERNEL);
 	if (!root)
 		return ERR_PTR(-ENOMEM);
-	__setup_root(4096, 4096, 4096, root, NULL, 1);
+	/* We don't use the stripesize in selftest, set it as sectorsize */
+	__setup_root(nodesize, sectorsize, sectorsize, root, NULL,
+			BTRFS_ROOT_TREE_OBJECTID);
 	set_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state);
 	root->alloc_bytenr = 0;
 
@@ -1803,6 +1806,13 @@ static int cleaner_kthread(void *arg)
 		if (btrfs_need_cleaner_sleep(root))
 			goto sleep;
 
+		/*
+		 * Do not do anything if we might cause open_ctree() to block
+		 * before we have finished mounting the filesystem.
+		 */
+		if (!root->fs_info->open)
+			goto sleep;
+
 		if (!mutex_trylock(&root->fs_info->cleaner_mutex))
 			goto sleep;
 
@@ -2517,7 +2527,6 @@ int open_ctree(struct super_block *sb,
 	int num_backups_tried = 0;
 	int backup_index = 0;
 	int max_active;
-	bool cleaner_mutex_locked = false;
 
 	tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
 	chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
@@ -2797,7 +2806,7 @@ int open_ctree(struct super_block *sb,
 
 	nodesize = btrfs_super_nodesize(disk_super);
 	sectorsize = btrfs_super_sectorsize(disk_super);
-	stripesize = btrfs_super_stripesize(disk_super);
+	stripesize = sectorsize;
 	fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
 	fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
 
@@ -2996,13 +3005,6 @@ retry_root_backup:
 		goto fail_sysfs;
 	}
 
-	/*
-	 * Hold the cleaner_mutex thread here so that we don't block
-	 * for a long time on btrfs_recover_relocation.  cleaner_kthread
-	 * will wait for us to finish mounting the filesystem.
-	 */
-	mutex_lock(&fs_info->cleaner_mutex);
-	cleaner_mutex_locked = true;
 	fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
 					       "btrfs-cleaner");
 	if (IS_ERR(fs_info->cleaner_kthread))
@@ -3022,7 +3024,7 @@ retry_root_backup:
 	}
 
 	/*
-	 * Mount does not set all options immediatelly, we can do it now and do
+	 * Mount does not set all options immediately, we can do it now and do
 	 * not have to wait for transaction commit
 	 */
 	btrfs_apply_pending_changes(fs_info);
@@ -3062,8 +3064,10 @@ retry_root_backup:
 		ret = btrfs_cleanup_fs_roots(fs_info);
 		if (ret)
 			goto fail_qgroup;
-		/* We locked cleaner_mutex before creating cleaner_kthread. */
+
+		mutex_lock(&fs_info->cleaner_mutex);
 		ret = btrfs_recover_relocation(tree_root);
+		mutex_unlock(&fs_info->cleaner_mutex);
 		if (ret < 0) {
 			btrfs_warn(fs_info, "failed to recover relocation: %d",
 					ret);
@@ -3071,8 +3075,6 @@ retry_root_backup:
 			goto fail_qgroup;
 		}
 	}
-	mutex_unlock(&fs_info->cleaner_mutex);
-	cleaner_mutex_locked = false;
 
 	location.objectid = BTRFS_FS_TREE_OBJECTID;
 	location.type = BTRFS_ROOT_ITEM_KEY;
@@ -3186,10 +3188,6 @@ fail_cleaner:
 	filemap_write_and_wait(fs_info->btree_inode->i_mapping);
 
 fail_sysfs:
-	if (cleaner_mutex_locked) {
-		mutex_unlock(&fs_info->cleaner_mutex);
-		cleaner_mutex_locked = false;
-	}
 	btrfs_sysfs_remove_mounted(fs_info);
 
 fail_fsdev_sysfs:
@@ -3255,7 +3253,7 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
 		btrfs_warn_rl_in_rcu(device->dev_root->fs_info,
 				"lost page write due to IO error on %s",
 					  rcu_str_deref(device->name));
-		/* note, we dont' set_buffer_write_io_error because we have
+		/* note, we don't set_buffer_write_io_error because we have
 		 * our own ways of dealing with the IO errors
 		 */
 		clear_buffer_uptodate(bh);
@@ -4130,6 +4128,16 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 	 * Hint to catch really bogus numbers, bitflips or so, more exact checks are
 	 * done later
 	 */
+	if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
+		btrfs_err(fs_info, "bytes_used is too small %llu",
+		       btrfs_super_bytes_used(sb));
+		ret = -EINVAL;
+	}
+	if (!is_power_of_2(btrfs_super_stripesize(sb))) {
+		btrfs_err(fs_info, "invalid stripesize %u",
+		       btrfs_super_stripesize(sb));
+		ret = -EINVAL;
+	}
 	if (btrfs_super_num_devices(sb) > (1UL << 31))
 		printk(KERN_WARNING "BTRFS: suspicious number of devices: %llu\n",
 				btrfs_super_num_devices(sb));
@@ -4367,7 +4375,7 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root,
 		if (ret)
 			break;
 
-		clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS);
+		clear_extent_bits(dirty_pages, start, end, mark);
 		while (start <= end) {
 			eb = btrfs_find_tree_block(root->fs_info, start);
 			start += root->nodesize;
@@ -4402,7 +4410,7 @@ again:
 		if (ret)
 			break;
 
-		clear_extent_dirty(unpin, start, end, GFP_NOFS);
+		clear_extent_dirty(unpin, start, end);
 		btrfs_error_unpin_extent_range(root, start, end);
 		cond_resched();
 	}